INDEX

Explanations

references to the concept of "use" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.21

ships

-0.20

ly

-0.19

ship

-0.18

ness

-0.18

rim

-0.17

 useful

-0.17

 usual

-0.17

raz

-0.17

ishly

-0.16

POSITIVE LOGITS

fully

0.41

age

0.40

full

0.39

fulness

0.37

ful

0.36

able

0.33

FUL

0.32

lessly

0.30

ages

0.25

AGE

0.24

Activations Density 0.083%

references to the concept of "use" in various contexts

No Comments

No Known Activations